{"list":"other","total":94,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2012.15613","title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","created":"2020-12-31","cited_by_count":318},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"1906.03158","title":"Matching the Blanks: Distributional Similarity for Relation Learning","created":"2019-06-07","cited_by_count":272},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"id":"1810.10147","title":"FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation","created":"2018-10-24","cited_by_count":254},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"1906.06127","title":"DocRED: A Large-Scale Document-Level Relation Extraction Dataset","created":"2019-06-14","cited_by_count":239},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"1912.05372","title":"FlauBERT: Unsupervised Language Model Pre-training for French","created":"2019-12-11","cited_by_count":153},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"2009.05387","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","created":"2020-09-11","cited_by_count":109},{"id":"2009.13570","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","created":"2020-09-28","cited_by_count":89},{"id":"1906.02900","title":"Compositional Questions Do Not Necessitate Multi-hop Reasoning","created":"2019-06-07","cited_by_count":88},{"id":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"2010.05444","title":"OCNLI: Original Chinese Natural Language Inference","created":"2020-10-12","cited_by_count":86},{"id":"1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","created":"2017-03-31","cited_by_count":85},{"id":"2004.14602","title":"Look at the First Sentence: Position Bias in Question Answering","created":"2020-04-30","cited_by_count":84},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75},{"id":"1804.07927","title":"DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension","created":"2018-04-21","cited_by_count":71},{"id":"1801.04871","title":"Building a Conversational Agent Overnight with Dialogue Self-Play","created":"2018-01-15","cited_by_count":70},{"id":"1810.09957","title":"NSML: Meet the MLaaS platform with a real-world case study","created":"2018-10-08","cited_by_count":70},{"id":"2004.08056","title":"Dialogue-Based Relation Extraction","created":"2020-04-17","cited_by_count":68},{"id":"2002.11893","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","created":"2020-02-27","cited_by_count":66},{"id":"1603.04351","title":"Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations","created":"2016-03-14","cited_by_count":55},{"id":"2010.15925","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","created":"2020-10-29","cited_by_count":53},{"id":"2004.03490","title":"What do Models Learn from Question Answering Datasets?","created":"2020-04-07","cited_by_count":45},{"id":"1909.07005","title":"KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension","created":"2019-09-16","cited_by_count":43},{"id":"2010.12850","title":"CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers","created":"2020-10-24","cited_by_count":43},{"id":"2012.06154","title":"ParsiNLU: A Suite of Language Understanding Challenges for Persian","created":"2020-12-11","cited_by_count":42},{"id":"2010.08738","title":"RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling","created":"2020-10-17","cited_by_count":41},{"id":"2005.12503","title":"BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection","created":"2020-05-26","cited_by_count":39},{"id":"2004.03289","title":"KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding","created":"2020-04-07","cited_by_count":37},{"id":"2010.02534","title":"An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks","created":"2020-10-06","cited_by_count":33},{"id":"1905.10425","title":"Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark","created":"2019-05-24","cited_by_count":32},{"id":"1903.08445","title":"Left-to-Right Dependency Parsing with Pointer Networks","created":"2019-03-20","cited_by_count":21},{"id":"2011.00080","title":"Dynamic Data Selection for Curriculum Learning via Ability Estimation","created":"2020-10-30","cited_by_count":21},{"id":"2008.03979","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","created":"2020-08-10","cited_by_count":17},{"id":"1711.07010","title":"A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text","created":"2017-11-19","cited_by_count":13},{"id":"2004.03283","title":"A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events","created":"2020-04-07","cited_by_count":8},{"id":"2010.06122","title":"Asking Crowdworkers to Write Entailment Examples: The Best of Bad Options","created":"2020-10-13","cited_by_count":8},{"id":"2012.15621","title":"Open Korean Corpora: A Practical Report","created":"2020-12-31","cited_by_count":6},{"id":"2005.12898","title":"Analysis of the Penn Korean Universal Dependency Treebank (PKT-UD): Manual Revision to Build Robust Parsing Model in Korean","created":"2020-05-26","cited_by_count":1}],"next_cursor":null}